OG
Compiler Engineer
Accepting applicationsOho Group · United States
Full-Time Mid_senior AIC++aterf
Posted
4d ago
Category
Test
Experience
Mid_senior
Country
United States
Compiler Engineer
Overview:
We're partnering with a deep-tech company building foundational software for next-generation AI and high-performance compute workloads. Their work sits at the intersection of compiler technology, hardware abstraction, and accelerated compute performance — tackling some of the hardest unsolved problems in the GPU software stack.
As early engineering headcount, you'll have direct influence over core platform architecture and the opportunity to shape how the system scales. If you're drawn to low-level performance problems, cross-platform compiler challenges, and building infrastructure that matters at the hardware-software boundary, this is a rare opportunity to join before the noise.
About the role:
Design and implement compiler infrastructure focused on accelerating GPU workloads.
Create and streamline MLIR-based compilation passes targeting IP and GPU architectures.
Build and maximise LLVM backend components, particularly register allocation, instruction selection, and target specific optimizations.
About you:
5+ years compiler engineering experience, focused on GPU or hardware accelerator backends.
High level of skill in C++ and LLVM, particularly LLVM IR and pass infrastructure.
Experience working with high-level GPU kernel frameworks such as Triton, as well as practical knowledge of Claude Code or equivalent AI-assisted workflows.
Salary
Up to $300k salary, medical insurance, vision insurance, dental insurance, 401k
Remote or on-site (San Jose) depending on preference
Apply now as interviews are being scheduled.
#GPU #backend #LLVM #MLIR #TRITON #C++
Show more Show less
Overview:
We're partnering with a deep-tech company building foundational software for next-generation AI and high-performance compute workloads. Their work sits at the intersection of compiler technology, hardware abstraction, and accelerated compute performance — tackling some of the hardest unsolved problems in the GPU software stack.
As early engineering headcount, you'll have direct influence over core platform architecture and the opportunity to shape how the system scales. If you're drawn to low-level performance problems, cross-platform compiler challenges, and building infrastructure that matters at the hardware-software boundary, this is a rare opportunity to join before the noise.
About the role:
Design and implement compiler infrastructure focused on accelerating GPU workloads.
Create and streamline MLIR-based compilation passes targeting IP and GPU architectures.
Build and maximise LLVM backend components, particularly register allocation, instruction selection, and target specific optimizations.
About you:
5+ years compiler engineering experience, focused on GPU or hardware accelerator backends.
High level of skill in C++ and LLVM, particularly LLVM IR and pass infrastructure.
Experience working with high-level GPU kernel frameworks such as Triton, as well as practical knowledge of Claude Code or equivalent AI-assisted workflows.
Salary
Up to $300k salary, medical insurance, vision insurance, dental insurance, 401k
Remote or on-site (San Jose) depending on preference
Apply now as interviews are being scheduled.
#GPU #backend #LLVM #MLIR #TRITON #C++
Show more Show less
Similar Jobs
M
New College Grad - DRAM Product Reliability Characterization Engineer
Micron · Boise, United States, North America
K
Business Development Manager - Strategic Business Unit
KLA · Milpitas, United States, North America
I
Graduate Talent (GenAI Software Solutions Engineer)
Intel · Penang, Malaysia, Asia
AM
Material Handler III
Applied Materials · Austin, United States, North America